You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I would like to compute at each node of a graph the mean of (the features of) its k-hops neighbors.
There is a function for a 1-hop: avg_pool_neighbor_x
avg_pool_neighbor_x calls add_self_loops but maybe I know that my graph has already self-loops, so wouldn't it be more general to let this function have add_self_loops in its signature ? With the default add_self_loops = True, it would be backward compatible.
Is there a function to more generally do average pooling over the k-hops neighbors, and not only the 1-hop neighbors ?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi,
I would like to compute at each node of a graph the mean of (the features of) its k-hops neighbors.
There is a function for a 1-hop:
avg_pool_neighbor_x
avg_pool_neighbor_x
callsadd_self_loops
but maybe I know that my graph has already self-loops, so wouldn't it be more general to let this function haveadd_self_loops
in its signature ? With the defaultadd_self_loops = True
, it would be backward compatible.Is there a function to more generally do average pooling over the k-hops neighbors, and not only the 1-hop neighbors ?
Thanks for any help.
Beta Was this translation helpful? Give feedback.
All reactions